Codewhale is an open-source coding agent that runs in the terminal and can read repositories, edit files, execute commands, and inspect results while pursuing a task. Developers use it with hosted providers or local models, with controls for how much access it receives.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Hmbown/CodewhaleWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/hmbown/codewhale/computer)<a href="https://agentmods.dev/commands/hmbown/codewhale/computer"><img src="https://agentmods.dev/badge/commands/hmbown/codewhale/computer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/hmbown/codewhale/computer"><img src="https://agentmods.dev/badge/commands/hmbown/codewhale/computer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00010 | $0.00213 |
| Opus 5.5 | $0.00004 | $0.00085 |
| Sonnet 5.5 | $0.00002 | $0.00043 |
| Haiku 4.5 | $0.00001 | $0.00021 |
Grade A, and why
computer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
$ARGUMENTS
- With no arguments or
status: report whether computer use is usable on the active computer — server reachable, platform, screen size, whether the Codewhale Computer Use app is doing the work (via), and which permissions or platform tools are missing (request_access) — without taking any action. - With
look: take one screenshot of the active computer and describe what is on screen. - With
computers: list registered computers (computer {action:"list"}) and say which one is active; every tool also takescomputerto switch. - Anything else (clicking, typing, operating apps, recording) goes through the computer-use skill's observe-act-verify loop with per-action approval. A denied permission or a missing tool fails closed and is reported, never retried blindly.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed d9a2c13aff1a
- 1mo ago Changed · +1 lines 5beab0ab5538
- 1mo ago Changed · +6 lines ea9bf0e6df6e
- 1mo ago First seen · 14 lines · 10 tokens per session scan A 69803a70be52
computer is a command published in the GitHub repository Hmbown/Codewhale (41,035 stars, last pushed 18d ago), licensed MIT. It adds 10 tokens to every session and 213 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other commands, from other repositories
role
Set this Claude session's agent-bus role so other sessions can address it (e.g. /role frontend, /role backend, /role tester).
auto-insights
Show or configure auto-generated insights from the claudectl brain — friction patterns, suggested rules, and workflow improvements.
brain
Toggle the claudectl brain gate on/off/auto for this session.
brain-stats
Show claudectl brain learning metrics — accuracy, correction rate, and effectiveness.
inbox
Drain pending agent-bus messages addressed to this session's role.
sessions
Show status of all active Claude Code sessions (cost, health, context usage).